ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

ERNIE 5.0vsGemini 3 Flash Preview

Gemini 3 Flash Preview leads 2 of 2 shared benchmarks. Gemini 3 Flash Preview has the larger context window (1.0M tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
0 – 2
Gemini 3 Flash Preview leads
Cheaper per token
list price, input + output
Larger context
Gemini 3 Flash Preview
1.0M tokens
Provider uptime (30d)
— · 100%
Baidu · Google
ERNIE 5.0
Baidu · released 2026-02-06
textvision
Context
128K
Max out
66K
Input /1M
Output /1M
Cached /1M
Scores
21 · 5 core
Gemini 3 Flash Preview
Google · released 2025-12-17
textvisionaudio
Context
1.0M
Max out
66K
Input /1M
Output /1M
Cached /1M
Scores
13 · 9 core
Quality

Benchmark matrix

BenchmarkERNIE 5.0Gemini 3 Flash PreviewΔEdge
Reported by both · 2
GPQA Diamond86.36% 90.4% -4 ptGemini 3 Flash Preview
AIME 202589.06% 95.2% -6.1 ptGemini 3 Flash Preview
Only ERNIE 5.0 reports · 19
MMLU-Pro83.8% not reported
ACEBench Chinese89.6% not reported
ACEBench English87.7% not reported
BBEH66.63% not reported
BFCL v466.47% not reported
BrowseComp-ZH64.71% not reported
ChineseSimpleQA86.03% not reported
HMMT 202579.58% not reported
HumanEval+94.48% not reported
Humanity's Last Exam25.81% not reported
IFEval93.35% not reported
LiveCodeBench v676.21% not reported
MBPP+82.54% not reported
Multi-IF85.56% not reported
MultiChallenge65.98% not reported
SimpleQA74.01% not reported
SpreadsheetBench40.08% not reported
Tau2-Bench78.79% not reported
ZebraLogic96.5% not reported
Only Gemini 3 Flash Preview reports · 9
SWE-bench Verifiednot reported78%
Humanity's Last Exam (no tools)not reported33.7%
FrontierMath Tier 4 v2 (Epoch AI run)not reported17.1% epoch
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported51.2% epoch
MMMU-Pronot reported81.2%
OTIS Mock AIME 2024-2025 (Epoch AI run)not reported95.6% epoch
SimpleQA Verifiednot reported68.7%
SWE-bench Verified (Epoch AI run)not reported75.4% epoch
Terminal-Bench 2.0not reported47.6%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is ERNIE 5.0 minus Gemini 3 Flash Preview in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecERNIE 5.0Gemini 3 Flash PreviewEdge
Context window128K tokens1.0M tokensGemini 3 Flash Preview
Max output66K tokens66K tokensTie
Input price / 1M
Output price / 1M
Cached input / 1M
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
Modalitiestext · visiontext · vision · audioGemini 3 Flash Preview
Released2026-02-062025-12-17
Cited benchmark scores2113
Reliability

Provider status

All providers
More matchups

Gemini 3 Flash Preview vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run ERNIE 5.0 and Gemini 3 Flash Preview on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.